Update README.md

README.md

@@ -2,16 +2,27 @@
 
 ## Submission Details
 
-
+### Summary 
 This repository contains all the files committed for my final CPSC 330 assignment at UBC. I am not breaching any privacy policies at UBC because this assignment was very open-ended and all solutions were purely custom developed by my partner, Raghav (I give credit to him for working with me), and I. The main code is located at `hw8.ipynb`. There is also a full-blown explanation of the code in `exercise3_blog_post.ipynb`, explaining in simple English terminology, the purpose of the data collection and analysis, how the data was peprocessed and how hyperparameters were tuned, as well as resulting predictions and accuracy of these predictions based on certain metrics used.
 
 Now ofcourse, you could argue that the hyperparameters could be tuned better or there are alternative ways I could have prre-processed the data before passing it into the models however, this is just the solution(s) we came up with given the time constraints of the assignment. We were also asked to use and compare only three models depending on whether we were solving a categorical or regression problem, which is why we limited to using 3 models. Given that the course is complete, I plan to use better hyperparameters and pre-process the data in a better way to obtain more accurate predictions with the test sets in the data. I will use this repository as a way to update this code as I make the aforementioned changes.
 
+### Ethical Considerations
+
 In addition to that, I would also like to state that I have remained very integral and cconsiderate of the distinction between our training and test data, such that test data was never previously viewed, tweaked or used in training the models. There are major ethical considerations in this realm, such that test sets shall only be used for testing the accuracy of models and not actually training the model (commonly referred to as The Golden Rule), which can skew prediction in accuracy in favour of the model. Therefore, I have adhered to these global ethical guidelines, supervised by our TAs and professor, to truly test how well our models perform. 
 
+
+### The Data and Model Predictions
+
 Please watch this repository for updates in the code and explanation in the near future as I try to make the model more accurate in its predictions.
 
-Data was generously obtained from Kaggle and is located [here](./)
+Data was generously obtained from Kaggle and is located [here](./AB_NYC_2019.csv). The dataset can also be viewed directly in [Kaggle](https://www.kaggle.com/dgomonov/new-york-city-airbnb-open-data).
+
+### The Purpose of these Models
+
+The purpose of this model is two-fold:
+1) 
+
 
 Please enter details of your submission here, per the [homework submission instructions](https://github.students.cs.ubc.ca/cpsc330-2019w-t2/home/blob/master/docs/homework_instructions.md).